CN104200816A - Speech control method and system - Google Patents
Speech control method and system Download PDFInfo
- Publication number
- CN104200816A CN104200816A CN201410374890.2A CN201410374890A CN104200816A CN 104200816 A CN104200816 A CN 104200816A CN 201410374890 A CN201410374890 A CN 201410374890A CN 104200816 A CN104200816 A CN 104200816A
- Authority
- CN
- China
- Prior art keywords
- signal
- mixed audio
- audio signal
- intensity
- predeterminated frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a speech control method. When mixed audio-video signals are detected, a terminal obtains intensities or proportions of audio signals at preset frequencies in the detected mixed audio-video signals; the terminal responds to the detected mixed audio-video signals when the intensities or proportions of the audio signals at the preset frequencies met the preset conditions. The invention further discloses a speech control system. By means of the speech control method and system, the speech control accuracy is improved.
Description
Technical field
The present invention relates to voice control field, relate in particular to sound control method and system.
Background technology
Development along with speech recognition technology, increasing terminal adopts voice to control, existing voice terminal is when detecting phonetic control command, phonetic control command that can be based on prestoring and the mapping relations between control routine, the corresponding control routine of phonetic control command that response detects.
But owing to there being the existence of the artificial sound source such as TV, sound equipment, radio in terminal operating environment, cause the phonetic control command receiving to be sent by sound sources such as above-mentioned TV, sound equipment, radios, the control routine of possible false triggering mistake, causes the voice precise control rate of terminal low.
Summary of the invention
Fundamental purpose of the present invention is to solve the low technical matters of voice precise control rate.
For achieving the above object, a kind of sound control method provided by the invention, described sound control method comprises the following steps:
When detecting mixed audio signal, terminal is obtained intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that described terminal response detects.
Preferably, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
When described intermediate-freuqncy signal is pulse signal, the mixed audio signal that described terminal response detects.
Preferably, described when detecting mixed audio signal, after terminal is obtained in the mixed audio signal detecting the intensity of the sound signal of each predeterminated frequency or the step of ratio, described sound control method also comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is stored as mechanical Sounnd source direction by the corresponding Sounnd source direction of the mixed audio signal detecting.
Preferably, when the intensity of the described sound signal at each predeterminated frequency or ratio do not meet default condition, the step that described terminal is stored as abnormal direction by the corresponding Sounnd source direction of the mixed audio signal detecting comprises:
When in the mixed audio signal detecting, the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Described terminal is recorded as abnormal direction by described Sounnd source direction;
When the number of times that is registered as abnormal direction at described sound source direction is greater than pre-set threshold value, described terminal is stored as mechanical Sounnd source direction by described Sounnd source direction.
Preferably, when the intensity of the described sound signal at each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that described terminal response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is obtained the infrared signal of predeterminated frequency;
When getting the infrared signal of predeterminated frequency, phonetic control command described in described terminal response.
Preferably, when the intensity of the described sound signal at each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that described terminal response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is determined the time point that detects mixed audio signal;
Described terminal is determined the image that image acquiring device gets at definite time point, and the image getting is processed, to obtain humanoid profile;
While getting humanoid profile the image from getting, the mixed audio signal that described terminal response detects.
In addition, for achieving the above object, the present invention also proposes a kind of speech control system, and described speech control system comprises:
Acquisition module, for when detecting mixed audio signal, obtains intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
Respond module, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, the mixed audio signal that response detects.
Preferably, described respond module comprises:
Determining unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
Response unit, for when described intermediate-freuqncy signal is pulse signal, the mixed audio signal that response detects.
Preferably, described speech control system also comprises memory module, while not meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, the corresponding Sounnd source direction of the mixed audio signal detecting is stored as to mechanical Sounnd source direction.
Preferably, described storage comprises:
Determining unit, while not meeting default condition for the intensity of the sound signal of each predeterminated frequency of mixed audio signal detecting or ratio, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Record cell, for being recorded as abnormal direction by described Sounnd source direction;
Storage unit, while being greater than pre-set threshold value for be registered as the number of times of abnormal direction at described sound source direction, is stored as mechanical Sounnd source direction by described Sounnd source direction.
Preferably, described respond module comprises:
Infrared signal acquiring unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, obtains the infrared signal of predeterminated frequency;
Response unit, for when getting the infrared signal of predeterminated frequency, responds described phonetic control command.
Preferably, described respond module comprises:
Determining unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, described terminal is determined the time point that detects mixed audio signal;
Processing unit, the image getting at definite time point for image acquiring device, and the image getting is processed, to obtain humanoid profile;
Response unit, while getting humanoid profile for the image from getting, the mixed audio signal that response detects.
The sound control method that the present invention proposes, when detecting mixed audio signal, terminal is obtained intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting, and when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that described terminal response detects, to guarantee that this mixed audio signal detecting is not that machine sends, and improves voice-operated accuracy.
Accompanying drawing explanation
Fig. 1 is the hardware configuration schematic diagram of the present invention's preferred embodiment of realizing voice-operated terminal;
Fig. 2 is the high-level schematic functional block diagram of the preferred embodiment of speech control system in Fig. 1;
Fig. 3 is the schematic flow sheet of the preferred embodiment of sound control method of the present invention.
The realization of the object of the invention, functional characteristics and advantage, in connection with embodiment, are described further with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
With reference to Fig. 1, Fig. 1 is the hardware configuration schematic diagram of the present invention's preferred embodiment of realizing voice-operated terminal.
This terminal 1 comprises processing unit 11, storage unit 12, voice pickup unit 13 and speech control system 14.
Voice pickup unit 13, during for vibrations receiving sound wave, the electric signal that vibrations are produced is converted to sound signal.
Storage unit 12, for storaged voice control system 14 and service data thereof, default condition and default frequency, the mapping relations between phonetic control command and control routine.It is emphasized that this storage unit 12 can be both an independent memory storage, can be also the general designation of a plurality of different memory storages, and therefore not to repeat here.
This processing unit 11, be used for calling and carry out this speech control system 14, when voice pickup unit 13 detects mixed audio signal, substitute the default frequency of cell stores and default condition, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition in the mixed audio signal detecting, respond described mixed audio signal.This processing unit 11 and storage unit 12 can be respectively both independent unit, also can integrate, and formed a controller, and therefore not to repeat here.
The invention provides a kind of speech control system.
With reference to Fig. 2, Fig. 2 is the high-level schematic functional block diagram of the preferred embodiment of speech control system in Fig. 1.
It is emphasized that, to one skilled in the art, functional block diagram shown in Fig. 2 is only the exemplary plot of a preferred embodiment, and those skilled in the art, around the functional module of the speech control system 14 shown in Fig. 2, can carry out supplementing of new functional module easily; The title of each functional module is self-defined title, only for auxiliary each program function piece of understanding this speech control system 14, be not used in and limit technical scheme of the present invention, the core of technical solution of the present invention is, the function that the functional module of define name will be reached separately.
The speech control system 14 that the present embodiment proposes, comprising:
Acquisition module 141, for when detecting mixed audio signal, obtains intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
In the present embodiment, acquisition module 141 obtains the sound signal of each predeterminated frequency in the mixed audio signal detecting intensity or ratio can realize in the following manner:
A, bandpass filter by different frequency is filtered the mixed audio signal detecting respectively, to obtain the sound signal of different frequency, for example default frequency is respectively 20HZ～300HZ, 300HZ～4KHZ and 4KHZ～20KHZ, by bandpass filter, can obtain 20HZ～300HZ, the first sound signal of 300HZ～4KHZ and 4KHZ～20KHZ, the second sound signal and the 3rd sound signal, the first sound signal, the amplitude a of the second sound signal and the 3rd sound signal, b, c is the first sound signal, the intensity of the second sound signal and the 3rd sound signal, and the first sound signal, the ratio of the second sound signal and the 3rd sound signal is respectively a/ (a+b+c), b/ (a+b+c), c/ (a+b+c).
B, based on default, obtain frequency the mixed audio signal detecting is carried out to Fourier transform, so that this mixed audio signal is converted to respective frequencies frequency-region signal, and the frequency-region signal based on detecting obtains ratio or the intensity of each corresponding frequency signal, this ratio, as described in a scheme, is obtained based on intensity.
Listed two kinds of enumerating obtain the intensity of the sound signal of each predeterminated frequency in the mixed audio signal detecting or ratio mode only for exemplary above; those skilled in the art utilize technological thought of the present invention; other modes that propose according to its real needs, to obtain the intensity of the sound signal of each predeterminated frequency in mixed audio signal or ratio all in protection scope of the present invention, are not carried out exhaustive one by one at this.
Respond module 142, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, the mixed audio signal that response detects.
In the present embodiment, this default condition Ke You manufacturer sets, and concrete example is as follows:
1) default condition is intermediate-freuqncy signal intensity or ratio are greater than the first pre-set threshold value, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, the intensity of high-frequency signal or ratio are less than the 3rd pre-set threshold value, respond module 142 is greater than the first pre-set threshold value for intensity or the ratio of the mixed audio signal intermediate-freuqncy signal detecting, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, when the intensity of high-frequency signal or ratio are less than the 3rd pre-set threshold value, the mixed audio signal that response detects.
2) default condition is intermediate-freuqncy signal intensity or ratio are greater than the first pre-set threshold value, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, respond module 142 is greater than the first pre-set threshold value for intensity or the ratio of the mixed audio signal intermediate-freuqncy signal detecting, and when the intensity of low frequency signal or ratio are less than the second pre-set threshold value, the mixed audio signal that response detects.
When listed two kinds of intensity in the sound signal of each predeterminated frequency enumerating or ratio meet default condition above; the mode of the mixed audio signal that response detects is only for exemplary; those skilled in the art utilize technological thought of the present invention; other modes that propose according to its real needs realize when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition; the technical scheme of the mixed audio signal that response detects all, in protection scope of the present invention, is not carried out exhaustive one by one at this.
The speech control system that the present embodiment proposes, when detecting mixed audio signal, acquisition module obtains intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting, and when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that respond module response detects, to guarantee that this mixed audio signal detecting is not that machine sends, and improves voice-operated accuracy.
Further, for improving voice-operated accuracy, described respond module 142 comprises:
Determining unit 1421, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
Response unit 1422, for when described intermediate-freuqncy signal is pulse signal, the mixed audio signal that response detects.
In the present embodiment, the calibration of this intermediate-freuqncy signal is 300HZ～4KHZ.In the present embodiment, pulse signal refers to discontinuous signal.When the intermediate-freuqncy signal in the mixed audio signal detecting is persistent signal, illustrate that plant equipment that this mixed audio signal detecting is continuous service is sent, as vent fan, motor and/or electric fan etc.
It will be understood by those skilled in the art that, while speaking due to user, the time interval of speaking is substantially constant, now, when described intermediate-freuqncy signal is pulse signal, the pulse interval of intermediate-freuqncy signal described in determining unit 1421, while mating with the default time interval in definite time interval, the mixed audio signal that described respond module 1422 responses detect.
Further, for improving voice-operated accuracy, described speech control system also comprises memory module, while not meeting default condition for the intensity in the sound signal of each predeterminated frequency or ratio, the corresponding Sounnd source direction of the mixed audio signal detecting is stored as to mechanical Sounnd source direction.
In the present embodiment, when the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, illustrate that the current mixed audio signal detecting is that machine sends, and now, is stored as mechanical Sounnd source direction by the corresponding Sounnd source direction of the mixed audio signal detecting.It will be understood by those skilled in the art that, user sends abnormal direction recording instruction to terminal, the control module of terminal is when detecting abnormal direction recording instruction, controlling voice pickup unit 13 rotates according to default direction, when the intensity of memory module sound signal of each predeterminated frequency in the mixed audio signal detecting or ratio do not meet default condition, the current direction of voice pickup unit 13 is stored as to mechanical Sounnd source direction.
Further, for improving voice-operated accuracy, described respond module 142 also meets default condition for intensity or the ratio of the sound signal at each predeterminated frequency, and when the Sounnd source direction of the mixed audio signal detecting does not mate with the mechanical Sounnd source direction prestoring, the mixed audio signal that response detects.
Further, for improving voice-operated accuracy, described memory module comprises:
Determining unit, while not meeting default condition for the intensity of the sound signal of each predeterminated frequency of mixed audio signal detecting or ratio, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Record cell, for being recorded as abnormal direction by described Sounnd source direction;
Storage unit, while being greater than pre-set threshold value for be registered as the number of times of abnormal direction at described sound source direction, is stored as mechanical Sounnd source direction by described Sounnd source direction.
In the present embodiment, while not meeting default condition due to the intensity of the sound signal of each predeterminated frequency in the mixed audio signal detecting or ratio, this sound signal detecting may be sent as mobile phone etc. by mobile terminal, when therefore the number of times that is registered as abnormal direction at current Sounnd source direction is greater than pre-set threshold value, the sound signal that current Sounnd source direction sends be solid mechanical send as motor etc., now, current Sounnd source direction is recorded as to mechanical Sounnd source direction.
Further, for improving voice-operated accuracy, described respond module 142 comprises:
Infrared signal acquiring unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, obtains the infrared signal of predeterminated frequency;
In the present embodiment, preferably by infrared sensor, obtain the infrared signal of predeterminated frequency, because people is homeothermal animal, the frequency of the infrared signal detecting is certain, when infrared sensor detects infrared signal, obtain the frequency of the infrared signal detecting, when the frequency of infrared signal is in the scope of default (human body infrared frequency), can illustrate that the infrared ray detecting is that human body gives out, think and have people in the running environment of this terminal, or infrared sensor is set to only to receive the sensor of the infrared signal of a certain frequency range, this frequency range belongs to the scope of human body infrared frequency, when receiving infrared signal, think and have people in the running environment of this terminal.
In the present embodiment, a plurality of infrared detecting devices can be set, the direction that each infrared detecting device is corresponding different, to detect whether there is people in different surveyed areas; Or this infrared detecting device is wide-angle infrared detecting device, can receive the infrared ray of the thermal source transmission of indoor different angles; Or infrared detecting device is unidirectional infrared sensor, only can detect the infrared ray of fixed-direction, can control this infrared detecting device and rotate according to default rotation direction (as clockwise direction), to receive the infrared signal of different directions.
Response unit, for when getting the infrared signal of predeterminated frequency, responds described phonetic control command.
It will be appreciated by persons skilled in the art that and improve voice-operated accuracy, response unit comprises: feature acquiring unit, for when getting the infrared signal of predeterminated frequency, obtains the sound characteristic of the mixed audio signal detecting; Response unit, for the vocal print feature getting when default sound characteristic mates, the mixed audio signal that response detects.This sound characteristic can be frequency, acoustic pressure or the sound pressure level etc. of vocal print feature, phonetic control command.
Further, for improving voice-operated accuracy, described respond module 142 comprises:
Determining unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, described terminal is determined the time point that detects mixed audio signal;
Processing unit, the image getting at definite time point for image acquiring device, and the image getting is processed, to obtain humanoid profile;
In the present embodiment, change color in image based on getting generates corresponding profile, and this profile and default humanoid profile are compared, at this profile during with default humanoid outline, the profile of determining this generation is humanoid profile, or the profile of this generation and default feature contour are compared, as contouring head and hand profile etc., when the profile generating mates with feature contour, the profile of determining this generation is humanoid profile.
Response unit, while getting humanoid profile for the image from getting, the mixed audio signal that response detects.
In the present embodiment, can, when getting humanoid profile, determine the lip contour in the image getting, and whether definite lip contour changes, when lip contour changes, explanation is that people is occurring, the mixed audio signal now detecting described in response.Be that described response unit comprises: determine subelement, while getting humanoid profile for the image from getting, the humanoid profile based on getting, determines described in the image getting, whether lip contour changes; Response subelement, for when determining described in the image getting, whether lip contour changes, the mixed audio signal that response detects.
In addition, the present invention also provides a kind of sound control method.
With reference to Fig. 3, the schematic flow sheet of the preferred embodiment that Fig. 3 is sound control method of the present invention.
The sound control method that the present embodiment proposes, comprises the following steps:
Step S10, when detecting mixed audio signal, terminal is obtained intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
In the present embodiment, intensity or the ratio of obtaining the sound signal of each predeterminated frequency in the mixed audio signal detecting can realize in the following manner:
A, bandpass filter by different frequency is filtered the mixed audio signal detecting respectively, to obtain the sound signal of different frequency, for example default frequency is respectively 20HZ～300HZ, 300HZ～4KHZ and 4KHZ～20KHZ, by bandpass filter, can obtain 20HZ～300HZ, the first sound signal of 300HZ～4KHZ and 4KHZ～20KHZ, the second sound signal and the 3rd sound signal, the first sound signal, the amplitude a of the second sound signal and the 3rd sound signal, b, c is the first sound signal, the intensity of the second sound signal and the 3rd sound signal, and the first sound signal, the ratio of the second sound signal and the 3rd sound signal is respectively a/ (a+b+c), b/ (a+b+c), c/ (a+b+c).
B, based on default, obtain frequency the mixed audio signal detecting is carried out to Fourier transform, so that this mixed audio signal is converted to respective frequencies frequency-region signal, and the frequency-region signal based on detecting obtains ratio or the intensity of each corresponding frequency signal, this ratio, as described in a scheme, is obtained based on intensity.
Listed two kinds of enumerating obtain the intensity of the sound signal of each predeterminated frequency in the mixed audio signal detecting or ratio mode only for exemplary above; those skilled in the art utilize technological thought of the present invention; other modes that propose according to its real needs, to obtain the intensity of the sound signal of each predeterminated frequency in mixed audio signal or ratio all in protection scope of the present invention, are not carried out exhaustive one by one at this.
Step S20, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that described terminal response detects.
In the present embodiment, this default condition Ke You manufacturer sets, and concrete example is as follows:
1) default condition is intermediate-freuqncy signal intensity or ratio are greater than the first pre-set threshold value, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, the intensity of high-frequency signal or ratio are less than the 3rd pre-set threshold value, respond module 142 is greater than the first pre-set threshold value for intensity or the ratio of the mixed audio signal intermediate-freuqncy signal detecting, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, when the intensity of high-frequency signal or ratio are less than the 3rd pre-set threshold value, the mixed audio signal that response detects.
2) default condition is intermediate-freuqncy signal intensity or ratio are greater than the first pre-set threshold value, the intensity of low frequency signal or ratio are less than the second pre-set threshold value, respond module 142 is greater than the first pre-set threshold value for intensity or the ratio of the mixed audio signal intermediate-freuqncy signal detecting, and when the intensity of low frequency signal or ratio are less than the second pre-set threshold value, the mixed audio signal that response detects.
When listed two kinds of intensity in the sound signal of each predeterminated frequency enumerating or ratio meet default condition above; the mode of the mixed audio signal that response detects is only for exemplary; those skilled in the art utilize technological thought of the present invention; other modes that propose according to its real needs realize when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition; the technical scheme of the mixed audio signal that response detects all, in protection scope of the present invention, is not carried out exhaustive one by one at this.
The sound control method that the present embodiment proposes, when detecting mixed audio signal, terminal is obtained intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting, and when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that described terminal response detects, to guarantee that this mixed audio signal detecting is not that machine sends, and improves voice-operated accuracy.
Further, for improving voice-operated accuracy, described step S20 comprises:
Step S21, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
Step S22, when described intermediate-freuqncy signal is pulse signal, the mixed audio signal that described terminal response detects.
In the present embodiment, the calibration of this intermediate-freuqncy signal is 300HZ～4KHZ.In the present embodiment, pulse signal refers to discontinuous signal.When the intermediate-freuqncy signal in the mixed audio signal detecting is persistent signal, illustrate that plant equipment that this mixed audio signal detecting is continuous service is sent, as vent fan, motor and/or electric fan etc.
It will be understood by those skilled in the art that, while speaking due to user, the time interval of speaking is substantially constant, now, when described intermediate-freuqncy signal is pulse signal, step S22 comprises: when described intermediate-freuqncy signal is pulse signal, described terminal is determined the pulse interval of described intermediate-freuqncy signal; While mating with the default time interval in definite time interval, the mixed audio signal that described terminal response detects.
Further, for improving voice-operated accuracy, after described step S10, described sound control method also comprises:
Step S30, when the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is stored as mechanical Sounnd source direction by the corresponding Sounnd source direction of the mixed audio signal detecting.
In the present embodiment, when the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, illustrate that the current mixed audio signal detecting is that machine sends, and now, is stored as mechanical Sounnd source direction by the corresponding Sounnd source direction of the mixed audio signal detecting.It will be understood by those skilled in the art that, user sends abnormal direction recording instruction to terminal, when detecting abnormal direction recording instruction, described terminal control voice pickup unit 13 rotates according to default direction, when in the mixed audio signal detecting, the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is stored as mechanical Sounnd source direction by the current direction of voice pickup unit 13.
Further, for improving voice-operated accuracy, described step S20 comprises: intensity or ratio in the sound signal of each predeterminated frequency meet default condition, and when the Sounnd source direction of the mixed audio signal detecting does not mate with the mechanical Sounnd source direction prestoring, the mixed audio signal that described terminal response detects.
Further, for improving voice-operated accuracy, described step S30 comprises:
When in the mixed audio signal detecting, the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Described terminal is recorded as abnormal direction by described Sounnd source direction;
When the number of times that is registered as abnormal direction at described sound source direction is greater than pre-set threshold value, described terminal is stored as mechanical Sounnd source direction by described Sounnd source direction.
In the present embodiment, while not meeting default condition due to the intensity of the sound signal of each predeterminated frequency in the mixed audio signal detecting or ratio, this sound signal detecting may be sent as mobile phone etc. by mobile terminal, when therefore the number of times that is registered as abnormal direction at current Sounnd source direction is greater than pre-set threshold value, the sound signal that current Sounnd source direction sends be solid mechanical send as motor etc., now, current Sounnd source direction is recorded as to mechanical Sounnd source direction.
Further, for improving voice-operated accuracy, described step S20 comprises:
Step S23, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is obtained the infrared signal of predeterminated frequency;
In the present embodiment, preferably by infrared sensor, obtain the infrared signal of predeterminated frequency, because people is homeothermal animal, the frequency of the infrared signal detecting is certain, when infrared sensor detects infrared signal, obtain the frequency of the infrared signal detecting, when the frequency of infrared signal is in the scope of default (human body infrared frequency), can illustrate that the infrared ray detecting is that human body gives out, think and have people in the running environment of this terminal, or infrared sensor is set to only to receive the sensor of the infrared signal of a certain frequency range, this frequency range belongs to the scope of human body infrared frequency, when receiving infrared signal, think and have people in the running environment of this terminal.
In the present embodiment, a plurality of infrared detecting devices can be set, the direction that each infrared detecting device is corresponding different, to detect whether there is people in different surveyed areas; Or this infrared detecting device is wide-angle infrared detecting device, can receive the infrared ray of the thermal source transmission of indoor different angles; Or infrared detecting device is unidirectional infrared sensor, only can detect the infrared ray of fixed-direction, can control this infrared detecting device and rotate according to default rotation direction (as clockwise direction), to receive the infrared signal of different directions.
Step S24, when getting the infrared signal of predeterminated frequency, phonetic control command described in described terminal response.
It will be appreciated by persons skilled in the art that and improve voice-operated accuracy, step S22 comprises: when getting the infrared signal of predeterminated frequency, described terminal is obtained the sound characteristic of the mixed audio signal detecting; In the vocal print feature getting when default sound characteristic mates, the mixed audio signal that described terminal response detects.This sound characteristic can be frequency, acoustic pressure or the sound pressure level etc. of vocal print feature, phonetic control command.
Further, for improving voice-operated accuracy, described step S20 comprises:
Step S25, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is determined the time point that detects mixed audio signal;
Step S26, described terminal is determined the image that image acquiring device gets at definite time point, and the image getting is processed, to obtain humanoid profile;
In the present embodiment, change color in image based on getting generates corresponding profile, and this profile and default humanoid profile are compared, at this profile during with default humanoid outline, the profile of determining this generation is humanoid profile, or the profile of this generation and default feature contour are compared, as contouring head and hand profile etc., when the profile generating mates with feature contour, the profile of determining this generation is humanoid profile.
Step S27, while getting humanoid profile the image from getting, the mixed audio signal that described terminal response detects.
In the present embodiment, can, when getting humanoid profile, determine the lip contour in the image getting, and whether definite lip contour changes, when lip contour changes, explanation is that people is occurring, the mixed audio signal now detecting described in response.Be that described step S27 is included in while getting humanoid profile the image from getting, the humanoid profile of described terminal based on getting, determines described in the image getting, whether lip contour changes; When determining described in the image getting, whether lip contour changes, the mixed audio signal that described terminal response detects.
It should be noted that, in this article, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thereby the process, method, article or the system that make to comprise a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or be also included as the intrinsic key element of this process, method, article or system.The in the situation that of more restrictions not, the key element being limited by statement " comprising ... ", and be not precluded within process, method, article or the system that comprises this key element and also have other identical element.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that above-described embodiment method can add essential general hardware platform by software and realize, can certainly pass through hardware, but in a lot of situation, the former is better embodiment.Understanding based on such, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in a storage medium (as ROM/RAM, magnetic disc, CD), comprise that some instructions are with so that a station terminal equipment (can be mobile phone, computing machine, server, air conditioner, or the network equipment etc.) carry out the method described in each embodiment of the present invention.
These are only the preferred embodiments of the present invention; not thereby limit the scope of the claims of the present invention; every equivalent structure or conversion of equivalent flow process that utilizes instructions of the present invention and accompanying drawing content to do; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (12)
1. a sound control method, is characterized in that, described sound control method comprises the following steps:
When detecting mixed audio signal, terminal is obtained intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the mixed audio signal that described terminal response detects.
2. sound control method as claimed in claim 1, is characterized in that, when the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
When described intermediate-freuqncy signal is pulse signal, the mixed audio signal that described terminal response detects.
3. sound control method as claimed in claim 1, it is characterized in that, described when detecting mixed audio signal, after terminal is obtained in the mixed audio signal detecting the intensity of the sound signal of each predeterminated frequency or the step of ratio, described sound control method also comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is stored as mechanical Sounnd source direction by the corresponding Sounnd source direction of the mixed audio signal detecting.
4. sound control method as claimed in claim 3, it is characterized in that, when the intensity of the described sound signal at each predeterminated frequency or ratio do not meet default condition, the step that described terminal is stored as abnormal direction by the corresponding Sounnd source direction of the mixed audio signal detecting comprises:
When in the mixed audio signal detecting, the intensity of the sound signal of each predeterminated frequency or ratio do not meet default condition, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Described terminal is recorded as abnormal direction by described Sounnd source direction;
When the number of times that is registered as abnormal direction at described sound source direction is greater than pre-set threshold value, described terminal is stored as mechanical Sounnd source direction by described Sounnd source direction.
5. sound control method as claimed in claim 1, is characterized in that, when the intensity of the described sound signal at each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that described terminal response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is obtained the infrared signal of predeterminated frequency;
When getting the infrared signal of predeterminated frequency, phonetic control command described in described terminal response.
6. sound control method as claimed in claim 1, is characterized in that, when the intensity of the described sound signal at each predeterminated frequency or ratio meet default condition, the step of the mixed audio signal that described terminal response detects comprises:
When the intensity of the sound signal of each predeterminated frequency or ratio meet default condition, described terminal is determined the time point that detects mixed audio signal;
Described terminal is determined the image that image acquiring device gets at definite time point, and the image getting is processed, to obtain humanoid profile;
While getting humanoid profile the image from getting, the mixed audio signal that described terminal response detects.
7. a speech control system, is characterized in that, described speech control system comprises:
Acquisition module, for when detecting mixed audio signal, obtains intensity or the ratio of the sound signal of each predeterminated frequency in the mixed audio signal detecting;
Respond module, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, the mixed audio signal that response detects.
8. speech control system as claimed in claim 7, is characterized in that, described respond module comprises:
Determining unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, determines whether the intermediate-freuqncy signal in the mixed audio signal detecting is pulse signal;
Response unit, for when described intermediate-freuqncy signal is pulse signal, the mixed audio signal that response detects.
9. speech control system as claimed in claim 7, it is characterized in that, described speech control system also comprises memory module, while not meeting default condition for the intensity in the sound signal of each predeterminated frequency or ratio, the corresponding Sounnd source direction of the mixed audio signal detecting is stored as to mechanical Sounnd source direction.
10. speech control system as claimed in claim 9, is characterized in that, described storage comprises:
Determining unit, while not meeting default condition for the intensity of the sound signal of each predeterminated frequency of mixed audio signal detecting or ratio, described terminal is determined the Sounnd source direction of the mixed audio signal detecting;
Record cell, for being recorded as abnormal direction by described Sounnd source direction;
Storage unit, while being greater than pre-set threshold value for be registered as the number of times of abnormal direction at described sound source direction, is stored as mechanical Sounnd source direction by described Sounnd source direction.
11. speech control systems as claimed in claim 7, is characterized in that, described respond module comprises:
Infrared signal acquiring unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, obtains the infrared signal of predeterminated frequency;
Response unit, for when getting the infrared signal of predeterminated frequency, responds described phonetic control command.
12. speech control systems as claimed in claim 7, is characterized in that, described respond module comprises:
Determining unit, while meeting default condition for the intensity of the sound signal at each predeterminated frequency or ratio, described terminal is determined the time point that detects mixed audio signal;
Processing unit, the image getting at definite time point for image acquiring device, and the image getting is processed, to obtain humanoid profile;
Response unit, while getting humanoid profile for the image from getting, the mixed audio signal that response detects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410374890.2A CN104200816B (en) | 2014-07-31 | 2014-07-31 | Sound control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410374890.2A CN104200816B (en) | 2014-07-31 | 2014-07-31 | Sound control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104200816A true CN104200816A (en) | 2014-12-10 |
| CN104200816B CN104200816B (en) | 2017-12-22 |
Family
ID=52086097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410374890.2A Active CN104200816B (en) | 2014-07-31 | 2014-07-31 | Sound control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200816B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637480A (en) * | 2015-01-27 | 2015-05-20 | 广东欧珀移动通信有限公司 | voice recognition control method, device and system |
| WO2016201767A1 (en) * | 2015-06-15 | 2016-12-22 | 中兴通讯股份有限公司 | Voice control method and device, and computer storage medium |
| CN107274913A (en) * | 2017-05-26 | 2017-10-20 | 广东美的厨房电器制造有限公司 | A kind of sound identification method and device |
| CN109831709A (en) * | 2019-02-15 | 2019-05-31 | 杭州嘉楠耘智信息科技有限公司 | Sound source orientation method and device and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1288223A (en) * | 1999-09-14 | 2001-03-21 | 德国汤姆森-布兰特有限公司 | Device adaptive for direction characteristic used for speech voice control |
| CN201129826Y (en) * | 2007-11-20 | 2008-10-08 | 珠海格力电器股份有限公司 | Air conditioner control device |
| US7895041B2 (en) * | 2007-04-27 | 2011-02-22 | Dickson Craig B | Text to speech interactive voice response system |
| CN202110564U (en) * | 2011-06-24 | 2012-01-11 | 华南理工大学 | Intelligent household voice control system combined with video channel |
| CN102945672A (en) * | 2012-09-29 | 2013-02-27 | 深圳市国华识别科技开发有限公司 | Voice control system for multimedia equipment, and voice control method |
| CN103714811A (en) * | 2013-12-29 | 2014-04-09 | 广州视声电子科技有限公司 | Voice-control real-estate system method and device |
| CN103745723A (en) * | 2014-01-13 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Method and device for identifying audio signal |
| CN103944983A (en) * | 2014-04-14 | 2014-07-23 | 美的集团股份有限公司 | Error correction method and system for voice control instruction |
-
2014
- 2014-07-31 CN CN201410374890.2A patent/CN104200816B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1288223A (en) * | 1999-09-14 | 2001-03-21 | 德国汤姆森-布兰特有限公司 | Device adaptive for direction characteristic used for speech voice control |
| US7895041B2 (en) * | 2007-04-27 | 2011-02-22 | Dickson Craig B | Text to speech interactive voice response system |
| CN201129826Y (en) * | 2007-11-20 | 2008-10-08 | 珠海格力电器股份有限公司 | Air conditioner control device |
| CN202110564U (en) * | 2011-06-24 | 2012-01-11 | 华南理工大学 | Intelligent household voice control system combined with video channel |
| CN102945672A (en) * | 2012-09-29 | 2013-02-27 | 深圳市国华识别科技开发有限公司 | Voice control system for multimedia equipment, and voice control method |
| CN103714811A (en) * | 2013-12-29 | 2014-04-09 | 广州视声电子科技有限公司 | Voice-control real-estate system method and device |
| CN103745723A (en) * | 2014-01-13 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Method and device for identifying audio signal |
| CN103944983A (en) * | 2014-04-14 | 2014-07-23 | 美的集团股份有限公司 | Error correction method and system for voice control instruction |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637480A (en) * | 2015-01-27 | 2015-05-20 | 广东欧珀移动通信有限公司 | voice recognition control method, device and system |
| WO2016201767A1 (en) * | 2015-06-15 | 2016-12-22 | 中兴通讯股份有限公司 | Voice control method and device, and computer storage medium |
| CN107274913A (en) * | 2017-05-26 | 2017-10-20 | 广东美的厨房电器制造有限公司 | A kind of sound identification method and device |
| CN109831709A (en) * | 2019-02-15 | 2019-05-31 | 杭州嘉楠耘智信息科技有限公司 | Sound source orientation method and device and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104200816B (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910500B (en) | Method and device for voice control of device with microphone array | |
| CN104269172A (en) | Voice control method and system based on video positioning | |
| US11856379B2 (en) | Method, device and electronic device for controlling audio playback of multiple loudspeakers | |
| US9576591B2 (en) | Electronic apparatus and control method of the same | |
| CN106572411A (en) | Noise cancelling control method and relevant device | |
| CN110767225B (en) | Voice interaction method, device and system | |
| CN104267618A (en) | Voice control method and system based on infrared positioning | |
| CN104200816A (en) | Speech control method and system | |
| CN104165438A (en) | Air conditioner controlling method and system | |
| CN104978955A (en) | Voice control method and system | |
| CN104616660A (en) | Intelligent voice broadcasting system and method based on environmental noise detection | |
| CN105091208B (en) | Air conditioner wind speed control method and system | |
| CN109671430A (en) | Voice processing method and device | |
| CN105600638A (en) | People stranding fault recognition device and method of elevator | |
| CN113409800A (en) | Processing method and device for monitoring audio, storage medium and electronic equipment | |
| CN104200817B (en) | Sound control method and system | |
| CN111103807A (en) | Control method and device for household terminal equipment | |
| US11682414B1 (en) | Adjusting audio transparency based on content | |
| CN112866877B (en) | Speaker control method, speaker control device, electronic apparatus, and storage medium | |
| CN113766385B (en) | Earphone noise reduction method and device | |
| CN107757537B (en) | Sound control method and device for vehicle-mounted engine | |
| CN108777144B (en) | Sound wave instruction identification method, device, circuit and remote controller | |
| CN108919277B (en) | Indoor and outdoor environment identification method and system based on sub-ultrasonic waves and storage medium | |
| US11823703B2 (en) | System and method for processing an audio input signal | |
| CN113163282B (en) | Noise reduction pickup system and method based on USB |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |